Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5974 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3054. Min Range: -11.3054
Max Act: 11.3054. Min Act: -0.1700
Data Index: 6344273 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3054. Min Range: -11.3054
Max Act: 11.2429. Min Act: -0.1700
Data Index: 6574571 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3054. Min Range: -11.3054
Max Act: 11.1179. Min Act: -0.1700
Data Index: 3795889 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3054. Min Range: -11.3054
Max Act: 11.0554. Min Act: -0.1700
Data Index: 6830289 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3054. Min Range: -11.3054
Max Act: 11.0554. Min Act: -0.1700
Data Index: 5450744 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3054. Min Range: -11.3054
Max Act: 10.9929. Min Act: -0.1700
Data Index: 1397610 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3054. Min Range: -11.3054
Max Act: 10.9929. Min Act: -0.1700
Data Index: 4851162 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3054. Min Range: -11.3054
Max Act: 10.9929. Min Act: -0.1700
Data Index: 7216036 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3054. Min Range: -11.3054
Max Act: 10.9304. Min Act: -0.1700
Data Index: 1020775 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3054. Min Range: -11.3054
Max Act: 10.9304. Min Act: -0.1700
Data Index: 5619841 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3054. Min Range: -11.3054
Max Act: 10.9304. Min Act: -0.1700
Data Index: 6004786 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3054. Min Range: -11.3054
Max Act: 10.8679. Min Act: -0.1700
Data Index: 822148 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3054. Min Range: -11.3054
Max Act: 10.8679. Min Act: -0.1700
Data Index: 1163494 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3054. Min Range: -11.3054
Max Act: 10.8679. Min Act: -0.1700
Data Index: 2501395 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3054. Min Range: -11.3054
Max Act: 10.8054. Min Act: -0.1700
Data Index: 4082282 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3054. Min Range: -11.3054
Max Act: 10.8679. Min Act: -0.1700
Data Index: 8194943 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3054. Min Range: -11.3054
Max Act: 10.8679. Min Act: -0.1700
Data Index: 5041235 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3054. Min Range: -11.3054
Max Act: 10.8054. Min Act: -0.1700
Data Index: 6002882 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3054. Min Range: -11.3054
Max Act: 10.8054. Min Act: -0.1700
Data Index: 7190998 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3054. Min Range: -11.3054
Max Act: 10.7429. Min Act: -0.1700
Data Index: 5818547 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19